An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble
The purpose of this paper is to improve the accuracy of solving prediction tasks of the missing IoT data recovery. To achieve this, the authors have developed a new ensemble of neural network tools. It consists of two successive General Regression Neural Network (GRNN) networks and one neural-like s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/9/2625 |
| _version_ | 1797568815147515904 |
|---|---|
| author | Roman Tkachenko Ivan Izonin Natalia Kryvinska Ivanna Dronyuk Khrystyna Zub |
| author_facet | Roman Tkachenko Ivan Izonin Natalia Kryvinska Ivanna Dronyuk Khrystyna Zub |
| author_sort | Roman Tkachenko |
| collection | DOAJ |
| description | The purpose of this paper is to improve the accuracy of solving prediction tasks of the missing IoT data recovery. To achieve this, the authors have developed a new ensemble of neural network tools. It consists of two successive General Regression Neural Network (GRNN) networks and one neural-like structure of the Successive Geometric Transformation Model (SGTM). The principle of ensemble topology construction on two successively connected general regression neural networks, supplemented with an SGTM neural-like structure, is mathematically substantiated, which improves the accuracy of prediction results. The effectiveness of the method is based on the replacement of the summation of the results of the two GRNNs with a weighted summation, which improves the accuracy of the ensemble operation in general. A detailed algorithmic implementation of the ensemble method as well as a flowchart of its operation is presented. The parameters of the ensemble operation are determined by optimization using the brute-force method. Based on the developed ensemble method, the solution of the task of completing the partially missing values in the real monitoring dataset of the air environment collected by the IoT device is presented. By comparing the performance of the developed ensemble with the existing methods, the highest accuracy of its performance (by the parameters of Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) accuracy) among the most similar in this class has been proved. |
| first_indexed | 2024-03-10T20:02:26Z |
| format | Article |
| id | doaj.art-80b45ef9281a4816b2c44f69108c2ba9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:02:26Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-80b45ef9281a4816b2c44f69108c2ba92023-11-19T23:28:53ZengMDPI AGSensors1424-82202020-05-01209262510.3390/s20092625An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM EnsembleRoman Tkachenko0Ivan Izonin1Natalia Kryvinska2Ivanna Dronyuk3Khrystyna Zub4Department of Publishing Information Technologies, Lviv Polytechnic National University, 12 Bandera str., 79000 Lviv, UkraineDepartment of Publishing Information Technologies, Lviv Polytechnic National University, 12 Bandera str., 79000 Lviv, UkraineDepartment of Information Systems, Faculty of Management, Comenius University in Bratislava, 82005 Bratislava 25, SlovakiaDepartment of Automated Control Systems, Lviv Polytechnic National University, 12 Bandera str., 79000 Lviv, UkraineCenter of Information Support, Lviv Polytechnic National University, 12 Bandera str., 79000 Lviv, UkraineThe purpose of this paper is to improve the accuracy of solving prediction tasks of the missing IoT data recovery. To achieve this, the authors have developed a new ensemble of neural network tools. It consists of two successive General Regression Neural Network (GRNN) networks and one neural-like structure of the Successive Geometric Transformation Model (SGTM). The principle of ensemble topology construction on two successively connected general regression neural networks, supplemented with an SGTM neural-like structure, is mathematically substantiated, which improves the accuracy of prediction results. The effectiveness of the method is based on the replacement of the summation of the results of the two GRNNs with a weighted summation, which improves the accuracy of the ensemble operation in general. A detailed algorithmic implementation of the ensemble method as well as a flowchart of its operation is presented. The parameters of the ensemble operation are determined by optimization using the brute-force method. Based on the developed ensemble method, the solution of the task of completing the partially missing values in the real monitoring dataset of the air environment collected by the IoT device is presented. By comparing the performance of the developed ensemble with the existing methods, the highest accuracy of its performance (by the parameters of Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) accuracy) among the most similar in this class has been proved.https://www.mdpi.com/1424-8220/20/9/2625IoT sensorsmissing dataANN techniquesdata imputationGRNNSuccessive Geometric Transformation Model |
| spellingShingle | Roman Tkachenko Ivan Izonin Natalia Kryvinska Ivanna Dronyuk Khrystyna Zub An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble Sensors IoT sensors missing data ANN techniques data imputation GRNN Successive Geometric Transformation Model |
| title | An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble |
| title_full | An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble |
| title_fullStr | An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble |
| title_full_unstemmed | An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble |
| title_short | An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble |
| title_sort | approach towards increasing prediction accuracy for the recovery of missing iot data based on the grnn sgtm ensemble |
| topic | IoT sensors missing data ANN techniques data imputation GRNN Successive Geometric Transformation Model |
| url | https://www.mdpi.com/1424-8220/20/9/2625 |
| work_keys_str_mv | AT romantkachenko anapproachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT ivanizonin anapproachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT nataliakryvinska anapproachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT ivannadronyuk anapproachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT khrystynazub anapproachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT romantkachenko approachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT ivanizonin approachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT nataliakryvinska approachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT ivannadronyuk approachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble AT khrystynazub approachtowardsincreasingpredictionaccuracyfortherecoveryofmissingiotdatabasedonthegrnnsgtmensemble |